mark loads to pins as cold immediately

This does the posix_fadvise to kick pins out of the disk cache (to
avoid a double copy in RAM).

app/logger.py

@@ -5,40 +5,6 @@ import logging
 import sys
 import threading
 
-ANSI_NAMED_COLORS = {
-    'black':   '\033[30m',
-    'red':     '\033[31m',
-    'green':   '\033[32m',
-    'yellow':  '\033[33m',
-    'blue':    '\033[34m',
-    'magenta': '\033[35m',
-    'cyan':    '\033[36m',
-    'white':   '\033[37m',
-}
-
-ANSI_LEVEL_COLORS = {
-    'DEBUG':    ANSI_NAMED_COLORS['cyan'],
-    'INFO':     ANSI_NAMED_COLORS['green'],
-    'WARNING':  ANSI_NAMED_COLORS['yellow'],
-    'ERROR':    ANSI_NAMED_COLORS['red'],
-    'CRITICAL': ANSI_NAMED_COLORS['magenta'],
-}
-
-ANSI_RESET = '\033[0m'
-ANSI_BOLD  = '\033[1m'
-
-
-class ColoredFormatter(logging.Formatter):
-    def format(self, record):
-        color = ANSI_LEVEL_COLORS.get(record.levelname, '')
-        bold  = ANSI_BOLD if record.levelno >= logging.WARNING else ''
-        level_tag = f"{bold}{color}[{record.levelname}]{ANSI_RESET} "
-        message = super().format(record)
-        line_color = ANSI_NAMED_COLORS.get(getattr(record, 'color', ''), '')
-        if line_color:
-            return f"{level_tag}{line_color}{message}{ANSI_RESET}"
-        return level_tag + message
-
 logs = None
 stdout_interceptor = None
 stderr_interceptor = None
@@ -85,7 +51,7 @@ def on_flush(callback):
     if stderr_interceptor is not None:
         stderr_interceptor.on_flush(callback)
 
-def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool = False, color_logs: bool = True):
+def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool = False):
     global logs
     if logs:
         return
@@ -102,10 +68,8 @@ def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool
     logger = logging.getLogger()
     logger.setLevel(log_level)
 
-    formatter = ColoredFormatter("%(message)s") if color_logs else logging.Formatter("%(message)s")
-
     stream_handler = logging.StreamHandler()
-    stream_handler.setFormatter(formatter)
+    stream_handler.setFormatter(logging.Formatter("%(message)s"))
 
     if use_stdout:
         # Only errors and critical to stderr
@@ -113,7 +77,7 @@ def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool
 
         # Lesser to stdout
         stdout_handler = logging.StreamHandler(sys.stdout)
-        stdout_handler.setFormatter(formatter)
+        stdout_handler.setFormatter(logging.Formatter("%(message)s"))
         stdout_handler.addFilter(lambda record: record.levelno < logging.ERROR)
         logger.addHandler(stdout_handler)
 

comfy/cli_args.py

@@ -183,7 +183,6 @@ parser.add_argument("--multi-user", action="store_true", help="Enables per-user
 
 parser.add_argument("--verbose", default='INFO', const='DEBUG', nargs="?", choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'], help='Set the logging level')
 parser.add_argument("--log-stdout", action="store_true", help="Send normal process output to stdout instead of stderr (default).")
-parser.add_argument("--color-logs", action=argparse.BooleanOptionalAction, default=True, help="Enable ANSI colored log output in the terminal (default: enabled, use --no-color-logs to disable).")
 
 
 # The default built-in provider hosted under web/

comfy/ldm/modules/attention.py

@@ -741,12 +741,12 @@ optimized_attention = attention_basic
 if model_management.sage_attention_enabled():
     logging.info("Using sage attention")
     optimized_attention = attention_sage
-elif model_management.flash_attention_enabled():
-    logging.info("Using Flash Attention")
-    optimized_attention = attention_flash
 elif model_management.xformers_enabled():
     logging.info("Using xformers attention")
     optimized_attention = attention_xformers
+elif model_management.flash_attention_enabled():
+    logging.info("Using Flash Attention")
+    optimized_attention = attention_flash
 elif model_management.pytorch_attention_enabled():
     logging.info("Using pytorch attention")
     optimized_attention = attention_pytorch

comfy/model_management.py

@@ -1217,7 +1217,7 @@ def get_aimdo_cast_buffer(offload_stream, device):
 def get_pin_buffer(offload_stream):
     pin_buffer = STREAM_PIN_BUFFERS.get(offload_stream, None)
     if pin_buffer is None:
-        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3))
+        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3), mark_cold=False)
         STREAM_PIN_BUFFERS[offload_stream] = pin_buffer
     elif offload_stream is not None:
         event = getattr(pin_buffer, "_comfy_event", None)

main.py

@@ -17,7 +17,7 @@ import folder_paths
 import time
 from comfy.cli_args import enables_dynamic_vram
 from app.logger import setup_logger
-setup_logger(log_level=args.verbose, use_stdout=args.log_stdout, color_logs=args.color_logs)
+setup_logger(log_level=args.verbose, use_stdout=args.log_stdout)
 
 from app.assets.seeder import asset_seeder
 from app.assets.services import register_output_files
@@ -344,9 +344,9 @@ def prompt_worker(q, server_instance):
             # Log Time in a more readable way after 10 minutes
             if execution_time > 600:
                 execution_time = time.strftime("%H:%M:%S", time.gmtime(execution_time))
-                logging.info(f"Prompt executed in {execution_time}", extra={'color': 'green'})
+                logging.info(f"Prompt executed in {execution_time}")
             else:
-                logging.info("Prompt executed in {:.2f} seconds".format(execution_time), extra={'color': 'green'})
+                logging.info("Prompt executed in {:.2f} seconds".format(execution_time))
 
             if not asset_seeder.is_disabled():
                 paths = _collect_output_absolute_paths(e.history_result)

requirements.txt

@@ -1,4 +1,4 @@
-comfyui-frontend-package==1.44.19
+comfyui-frontend-package==1.43.18
 comfyui-workflow-templates==0.9.82
 comfyui-embedded-docs==0.5.0
 torch
@@ -23,7 +23,7 @@ SQLAlchemy>=2.0.0
 filelock
 av>=14.2.0
 comfy-kitchen>=0.2.8
-comfy-aimdo==0.4.3
+comfy-aimdo==0.4.5
 requests
 simpleeval>=1.0.0
 blake3